© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52210
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     _______,
    -0.10
    **),
    -0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.08
    ``,
    -0.07
    ä¸įä»ħèĥ½å¤Ł
    -0.07
    ardi
    -0.07
    ä¸įä»ħéľĢè¦ģ
    -0.07
    ä¹ĭæīĢ以
    -0.07
     [],
    -0.07
     наÑģÑĤолÑĮко
    -0.07
    POSITIVE LOGITS
    beit
    0.08
    )..
    0.08
    ׼ף
    0.08
     اÙĦبتÙĩ
    0.07
    ç´§åĽºä»¶
    0.07
     though
    0.07
    ä¸įåĪ°äºĨ
    0.07
    å®īåħ¨ç¬¬ä¸Ģ
    0.07
     thus
    0.07
    çªģæĺ¾
    0.07
    Activations Density 0.031%

    No Known Activations